© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57154
    Prev
    Next
    INDEX
    Explanations

    code dictionary values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.06
     (
    -0.06
    å°ıé»Ħ
    -0.06
    ↵
    -0.06
    erry
    -0.06
    ส
    -0.06
    ¯
    -0.05
    å®°
    -0.05
    à¸ľà¸¥
    -0.05
    äºĮæĺ¯
    -0.05
    POSITIVE LOGITS
    _HT
    0.09
    缸åħ³æ³ķå¾ĭ责任
    0.08
    SError
    0.08
    ฯ
    0.08
     TAH
    0.08
    inou
    0.08
    ikiem
    0.08
     thác
    0.08
    AttributeValue
    0.08
    htable
    0.08
    Activations Density 0.029%

    No Known Activations